Create a persistent research project. Returns a project_id that you can pass to all subsequent research_* calls. Projects survive across sessions — open it days later with research_project_continue and you get every prior finding, hypothesis, and open gap. Depth controls how aggressively the synt...
AI agents use research_project_create to create or update resources in Celiums Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Celiums Memory environment.
This tool creates and stores new persistent data (a research project with project_id, findings, hypotheses, and gaps) that persists across sessions. It is a reversible write operation—the project can presumably be deleted or archived—making it Write category rather than Destructive.
From the tool's definition Tool description states 'Create a persistent research project' and 'Returns a project_id that you can pass to all subsequent research_* calls. Projects survive across sessions', indicating creation and modification of persistent data structures.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access research_project_create gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Celiums Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for research_project_create:
{
"version": "1",
"default": "deny",
"tools": {
"research_project_create": {
"limits": [
{
"counter": "research_project_create_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}research_project_create stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create a persistent research project. Returns a project_id that you can pass to all subsequent research_* calls. Projects survive across sessions — open it days later with research_project_continue and you get every prior finding, hypothesis, and open gap. Depth controls how aggressively the synthesizer explores: overview (5 docs), standard (10 docs), deep (20+ docs with adversarial verification). It is categorised as a Write tool in the Celiums Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Celiums Memory MCP server in PolicyLayer and add a rule for research_project_create: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Celiums Memory. Nothing to install.
research_project_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the research_project_create rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for research_project_create. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
research_project_create is provided by the Celiums Memory MCP server (terrizoaguimor/celiums-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Celiums Memory, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
62 Celiums Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.